Alpamayo-1.5-10B
Alpamayo-1.5-10B is a 10 billion parameter chat model from nvidia, released March 3, 2026. Alpamayo-1.5-10B is an open-weights chat model with roughly 10 billion parameters.
by nvidia · 10B parameters
Best for
Ways to use Alpamayo-1.5-10B in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your nvidia API key. osFoundry discovers Alpamayo-1.5-10B automatically — assign it to a Maestro role (router, direct, orchestrator, or fallback) in the Pipeline tab and it is live in every chat. Your key, your provider account — no token markup.
Deploy a dedicated endpoint
Alpamayo-1.5-10B is open-weights — run it locally for free, or deploy a dedicated GPU endpoint in your workspace for reserved capacity with no rate limits.
Use it in a Room App
Room Apps declare AI features in their manifest, then call them with invokeAI:
import { invokeAI } from '@osfoundry/app-sdk'
// 'summarize' is an AI feature declared in your app manifest.
const result = await invokeAI('summarize', userText)
Call it from your own apps
Once a model is wired into your workspace you can host it as an API and reach it from your own services, scripts, or CI — outside osFoundry.
What hardware can run Alpamayo-1.5-10B
Alpamayo-1.5-10B runs on a single 16GB consumer GPU (~6 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~24 GB).
Alpamayo-1.5-10B vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about Alpamayo-1.5-10B
Is Alpamayo-1.5-10B free to use?
Alpamayo-1.5-10B is free to run locally on your own hardware. Hosted access through osFoundry is metered (input Free (local), output Free (local)). You can switch between local and hosted at any time.
Can I use Alpamayo-1.5-10B commercially?
Commercial use is allowed with conditions. Licence terms not specified — verify the upstream model card before commercial use. Check upstream documentation.
How much VRAM does Alpamayo-1.5-10B need?
Approximately 6 GB at Q4 quantisation, or 24 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run Alpamayo-1.5-10B locally?
Yes. Alpamayo-1.5-10B is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is Alpamayo-1.5-10B best at?
Alpamayo-1.5-10B is well-suited to robotics.
How do I use Alpamayo-1.5-10B in osFoundry?
Paste your nvidia API key in the key dialog (or deploy the open weights for self-hostable models), assign Alpamayo-1.5-10B to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by nvidia on March 3, 2026. Source: https://huggingface.co/nvidia/Alpamayo-1.5-10B